Belvedir's mission is to make the creation and deployment of AI models accessible to everyone. To achieve this we build autonomous systems for cleaning raw data, creating benchmarks, asynchronous RL, test-time training, inference optimization, and much more.
We work with startups, enterprises, and some of the world's leading applied AI companies. We have raised a seed round from an amazing group of notable VCs and angels.
About the role
- Design and run training experiments: SFT, distillation, preference tuning, and RL on customer tasks.
- Build the pipelines that turn raw customer data into high-quality training sets: collection, cleaning, filtering, and synthesis.
- Build task-specific evaluations and use them to drive decisions about data and training recipes.
- Turn one-off customer wins into repeatable training recipes and tooling the whole team can use.
- Work directly with customers and founders to decide what to train next.
What we are looking for
- Experience with LLM training: post-training, RL, RLHF, evals, or synthetic data, in industry or research.
- You have trained or fine-tuned models on real, messy data.
- You know what makes an eval trustworthy, and how models game one that is not.
- You can work directly with customers and turn what you hear into what to train next.
- You own problems end to end and ship. Founder or early-engineer experience is a plus.
#J-18808-Ljbffr